A Java framework for building agentic, workflow and multi-agent AI applications on top of Spring AI.
hexabot-ai/Hexabot
An automation platform for building agentic AI workflows in YAML that run across conversational channels, with tools, MCP, memory and RAG.
- Stars
- 1,157
- Forks
- 238
- Open issues
- 28
- Last commit
- 29 days ago
What is it?
Hexabot is an automation platform for building and running AI-driven workflows. Workflows are defined in YAML with typed runtime contracts, and they are executed through actions whose inputs, outputs and settings are validated with schemas. Reusable bindings separate capability and configuration from task logic, so the same workflow can be wired to different tools or models.
The platform combines workflows, actions, agents and conversational channels in a single runtime. It includes explicit memory definitions, Model Context Protocol (MCP) integration points for tool and context interoperability, and multi-channel support for chat interfaces. Zod is used broadly for validation and shared contracts.
For data, TypeORM is the standard backend layer, with SQLite as the default local database and Postgres for production. A CLI scaffolds new projects and starts a local dev environment with an admin UI and API on port 3000.
Key features
- 01YAML-defined agentic workflows with typed runtime contracts.
- 02Schema-validated actions for inputs, outputs and settings.
- 03Reusable bindings that separate capabilities from task logic.
- 04Explicit memory definitions integrated into the runtime.
- 05MCP integration points for tool and context interoperability.
- 06TypeORM data layer with SQLite locally and Postgres for production.
Use cases
- Building chatbots that run multi-step AI workflows across messaging channels.
- Wiring LLM agents to external tools through MCP.
- Automating routine conversational tasks with memory and retrieval.
- Prototyping agent workflows locally before deploying with Postgres.
Quick start
- 1
Install the Hexabot CLI globally
npm install -g @hexabot-ai/cli - 2
Create a new project (requires an interactive terminal)
hexabot create my-project - 3
Enter the project folder, then start it in dev mode
hexabot dev
Things to know
- The license is FCL-1.0-ALv2, a source-available license rather than a standard open-source license, so check its terms before commercial use.
- Project creation prompts for admin credentials and needs an interactive terminal, so it cannot run directly in CI.
- It requires Node.js ^24.17.0.
Topics
FAQ
- What is Hexabot?
- An automation platform for building agentic AI workflows in YAML that run across conversational channels, with tools, MCP, memory and RAG. Hexabot is an automation platform for building and running AI-driven workflows. Workflows are defined in YAML with typed runtime contracts, and they are executed through actions whose inputs, outputs and settings are validated with schemas. Reusable bindings separate capability and configuration from task logic, so the same workflow can be wired to different tools or models.
- Is Hexabot free to use? What license does it have?
- Hexabot is open source under the Other license. Check the license terms before using it in commercial products.
- Is Hexabot still maintained?
- Actively maintained. The last commit to Hexabot was on Sep 23, 2026.
- What can I use Hexabot for?
- Building chatbots that run multi-step AI workflows across messaging channels. Wiring LLM agents to external tools through MCP. Automating routine conversational tasks with memory and retrieval. Prototyping agent workflows locally before deploying with Postgres.
- How do I install Hexabot?
- Install the Hexabot CLI globally: npm install -g @hexabot-ai/cli Create a new project (requires an interactive terminal): hexabot create my-project Enter the project folder, then start it in dev mode: hexabot dev
- Where can I get Hexabot?
- The source code and installation instructions are on GitHub: https://github.com/hexabot-ai/Hexabot
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Self-hostable personal AI assistant as a single Go binary, combining LLM chat, RAG knowledge bases, and agent loops for browsing, shell, and MCP tools.
An open-source LLM application devops platform for enterprises, covering workflows, RAG, agents, model management, evaluation and fine-tuning.
Open-source SDK for building and running AI agents in Python and TypeScript, with tools, MCP, memory, and model portability.
An open-source TypeScript framework and app stack for building autonomous AI agents, with a core runtime, plugins, and a local-first Eliza app.
TypeScript framework for building AI agents with memory, tools, MCP, RAG, voice and workflows, plus the VoltOps console for observability.